In this paper, we propose a novel two-step approach, called KFBin, for the binarization of document images based on the Kalman filtering (KF) technique. In the first step, a state space model is developed as a new document image representation, and then the Kalman filter is applied to track the positions of the foreground and background information and generate two corresponding outputs, which allows the enhancement of the foreground content leading to better legibility of text. Standard thresholding algorithms were used in the second step to generate binary images from the enhanced foreground components. The performance of the proposed approach is validated on a well-known dataset and evaluated using common image binarization quality metrics. Outstanding improvement of the binarization performances of several state-of-the-art binarization methods has been achieved by using the proposed approach. Experimental results point that the poor binarization results of egraded document images can be greatly improved by enhancing their quality.